autonomous-os

MOVED — canonical skill now lives in the platform skills tree.

Self-enroll a voice for speaker recognition. Activate ONLY when (a) a mic `Unknown Speaker:` turn carries a clear self-introduction ("I'm X", "my name is X", "tôi là X"...), (b) prior same-tag `[voice:voice_N]` turns can be combined with a now-named turn, (c) a Telegram voice-note carries an intro, OR (d) the user asks to list / forget / identify voices. Do NOT activate on bare `Unknown Speaker:` turns with no name and no prior same-tag history — those need only a short ack. Self-enrollment only.

Proactive coaching across hydration, breaks, meals AND posture. Use when an [activity] event fires (message starts with `[activity] Activity detected: <labels>.` — labels include drink, break, or sedentary raw labels like "using computer"; sedentary events may also carry a [posture_summary: {...}] block when the user has been at the computer long enough for posture to drift), or when the user asks if they should drink water / take a break / fix their posture. Thresholds are computed from per-user logs, never guessed.

Push Claude Code activity to the user's device (e.g. a lamp) over the LAN. The plugin POSTs semantic events to a companion daemon on the device (HTTP, port 5002); the device turns them into its own feedback (LED / round display / voice). Supports connecting a device, pushing usage, sending notifications, and tuning how/when the user is alerted. Triggers: "connect my device", "push my usage to my device", "notify my device", "send to my device", "mute my device", "warn me earlier", "set warning threshold to N", "stop the task done notification".

Control the device's RGB light when the user asks for a SPECIFIC color (e.g. "yellow", "red", "yellow", "red", "turn on color X", "enable X light"), an LED effect, or turning LEDs off. Do NOT use for ambiance/activity lighting (use Scene) or emotion expression (use Emotion).

Camera control — snapshot, stream, and privacy toggle. Trigger on "what do you see", "look at this", "take a photo", "don't look", "stop looking", "stop watching", "stop staring", "camera off", "camera on", "give me privacy". MUST call [HW:/camera/disable:{}] or [HW:/camera/enable:{}] when toggling — never just reply with text.

Coordinate with the Claude Buddy companion (Claude Desktop + Claude Code on the user's Mac) — voice-approve tool permission prompts and stay aware of Claude activity.

Route voice input from the realtime voice agent pipeline based on message tags.

Low-level speaker and microphone hardware control — adjust volume, play test tones, record raw audio. Do NOT use for TTS/speech (that is the Voice skill).

Control the user's Mac via the paired Autonomous Buddy companion app — open/close apps, navigate URLs in Chrome, type text into focused fields, fire keyboard shortcuts, show desktop notifications, write to clipboard, click named UI buttons via macOS Accessibility. Also covers vision-driven tasks (screenshot, find/click unlabelled UI, read text off the screen, drag) — those load `reference/vision.md` for the synchronous see-think-act loop. Use when the user explicitly asks the device to do something on their COMPUTER (e.g. "open Chrome", "go to Gmail", "join Meet", "close Slack", "type … into my Mac", "copy … to clipboard", "click the blue button on my screen", "what's on my Mac right now?"). Do NOT use for hardware control of the device itself (LED, scene, emotion, music, servo) — those are separate skills. Do NOT use if no Mac is paired (the device's web UI shows pairing status under the Buddy card).

Use when the user asks to change eye expression directly, show info text on the display (time, weather, timer), or manually control the round LCD — NOT needed for normal conversation (Emotion skill auto-syncs eyes).

Express emotion through coordinated servo + LED + display eyes on EVERY conversational response. This is the PRIMARY response skill that makes the device feel alive. Do NOT use for ambiance lighting (use Scene) or custom LED colors (use LED Control).

Guard mode for security monitoring. Two uses — (1) Toggle on/off when a friend says "guard mode", "watch the house", "I'm going out", or similar. (2) Handle any sensing event that carries a [guard-active] tag (e.g. [sensing:presence.enter][guard-active], [sensing:motion][guard-active]) with dramatic shock/curious emotion + Telegram broadcast. Do NOT fall back to normal sensing reactions while guard mode is on.

Query flow event logs to answer questions about past sensing events — "Have you seen anybody between 10pm and 12pm?", "Is there any motion in the last hour?", "What happened while I was away?".

Use to aim/point/look the device in a DIRECTION, toggle servo state (hold/resume/release), or play a named servo animation (nod/shake/etc). Directions are fixed named locations or axes — supported: desk, wall, left, right, up, down, center, user. Furniture and surfaces ("desk", "table", "floor", "ceiling", "wall", "door", "workspace") are ALWAYS directions, never tracking targets — map them to the closest of the supported names (table/workspace → desk). MUST use /servo/aim (not /servo/track) for: "look at the desk"→desk, "point at my table"→desk, "look at the wall"→wall, "look left"→left, "point up"→up, "look at me"→user. For following a movable OBJECT by vision (cup, phone, hand, person, pet) use servo-tracking instead. Compound: if user names a direction AND an object ("look at desk and follow cup"), fire THIS aim skill first, then tracking.

Manage the device's face recognition roster — enroll new faces (3 paths: user-supplied photo, agent-captured snapshot on user request, or HAL's familiar-stranger prompt) and maintain the enrolled set (status / remove / reset). All enrolled persons are friends; strangers stay unnamed until promoted via one of the enroll flows.

Tracks the USER's mood only — signals + synthesized decision from camera/voice/telegram. Do NOT use for emotion commands directed at the device ("show sad", "be happy", bare "sad now"); those go through emotion/SKILL.md and are never logged here. Music/wellbeing skills consume the latest decision.

Maps a detected user emotion — from facial expression (emotion.detected) OR speech (speech_emotion.detected) — into a mood signal logged via the Mood skill, then picks one response route (music / checkin / action). This is about the USER's emotion (input), NOT the device's own expression — that's emotion/SKILL.md.

TTS speech + mic/speaker mute for privacy. MUST trigger on meetings, calls, privacy, silence requests. "meeting"/"call"/"private" = mic+speaker mute. "be quiet"/"silent" = speaker mute only. Always call HW markers — never just text.

Tracks and analyzes behavioral patterns (habits) for known users based on their wellbeing, presence, posture, and activity history. Use when answering questions about a user's routines ("What are Leo's habits?", "Has Leo been keeping to his routine?", "Notice anything about my patterns?"), or when invoked from wellbeing/SKILL.md or posture/SKILL.md on a threshold nudge to refresh patterns and provide habit-aware phrasing. Also feeds music-suggestion/SKILL.md with `music_patterns` for personalized genre. Habit does NOT fire its own standalone nudge — it enriches wellbeing/posture threshold-nudge phrasing.

Activate predefined lighting scene presets (reading, focus, relax, movie, night, energize) when the user asks for activity-based or environment lighting. Scenes control both color temperature AND brightness. Do NOT use for specific colors (use LED Control) or emotion expression (use Emotion).

Use ONLY to follow/track/watch a movable physical OBJECT vision can recognize (cup, bottle, phone, hand, person, pen, book, remote, toy, keys, pet, a specific face). NEVER use for furniture or fixed locations (desk, table, wall, floor, ceiling, door, window, workspace, room) — those are directions; use servo-control /servo/aim. NEVER use for direction words (left, right, up, down, center). If the user combines a direction AND an object ("look at the desk and follow the cup", "point at the table and track the phone"), fire TWO markers in order — servo-control /servo/aim first, then /servo/track here. The verb "look at" is ambiguous — if what follows is furniture/location, route to servo-control instead.

Play and stop music from YouTube through the device's speaker on user request.

React to passive sensing events from the device — presence, sound, light, fire hazard. Events arrive as [sensing:<type>] messages and each gets an emotion marker + optional short line. Does NOT handle motion.activity (→ wellbeing) or emotion.detected / speech_emotion.detected (→ user-emotion-detection).

Detect which third-party connectors (Gmail, Google Calendar, Google Drive, Notion, Figma, Asana, Linear, GitHub, Ahrefs, …) are connected to this device, and use them to answer the user. Use when the user asks what's connected ("what connectors do I have", "is my gmail connected", "did I link figma"), or asks to read/act on a connected service ("check my gmail", "read my latest email", "what's on my calendar", "my recent drive files", "check figma", "look at my notion"). Discovers connectors by scanning the on-disk credential files, then routes: token services (Gmail/Calendar/Drive) are read + queried via curl; MCP services (Notion/Figma/Asana/Linear/GitHub) are used through their own agent tools.

Proactive music suggestion. Routed in by user-emotion-detection/SKILL.md (the router) on emotion.detected (camera) and speech_emotion.detected (voice) events when the synthesized mood is suggestion-worthy (sad/stressed/tired/excited/happy/bored) AND audio is idle AND cooldown is clear. Reads, decision, and writes share the same parallel batch in a single turn. Does NOT fire on motion.activity / [activity] events — those route to wellbeing/SKILL.md only. NOT for user-initiated music requests (those use the music skill).